spapr: Add "memop" hypercall

This adds a qemu-specific hypervisor call to the pseries machine
which allows to do what amounts to memmove, memcpy and xor over
regions of physical memory such as the framebuffer.

This is the simplest way to get usable framebuffer speed from
SLOF since the framebuffer isn't mapped in the VRMA and so would
otherwise require an hcall per 8 bytes access.

The performance is still not great but usable, and can be improved
with a more complex implementation of the hcall itself if needed.

This also adds some documentation for the qemu-specific hypercalls
that we add to PAPR along with a new qemu,hypertas-functions property
that mirrors ibm,hypertas-functions and provides some discoverability
for the new calls.

Note: I chose note to advertise H_RTAS to the guest via that mechanism.
This is done on purpose, the guest uses the normal RTAS interfaces
provided by qemu (including SLOF) which internally calls H_RTAS.

We might in the future implement part (or even all) of RTAS inside the
guest like IBM's firmware does and replace H_RTAS with some finer grained
set of private hypercalls.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Alexander Graf <agraf@suse.de>

docs/specs/ppc-spapr-hcalls.txt

@@ -0,0 +1,78 @@
+When used with the "pseries" machine type, QEMU-system-ppc64 implements
+a set of hypervisor calls using a subset of the server "PAPR" specification
+(IBM internal at this point), which is also what IBM's proprietary hypervisor
+adheres too.
+
+The subset is selected based on the requirements of Linux as a guest.
+
+In addition to those calls, we have added our own private hypervisor
+calls which are mostly used as a private interface between the firmware
+running in the guest and QEMU.
+
+All those hypercalls start at hcall number 0xf000 which correspond
+to a implementation specific range in PAPR.
+
+- H_RTAS (0xf000)
+
+RTAS is a set of runtime services generally provided by the firmware
+inside the guest to the operating system. It predates the existence
+of hypervisors (it was originally an extension to Open Firmware) and
+is still used by PAPR to provide various services that aren't performance
+sensitive.
+
+We currently implement the RTAS services in QEMU itself. The actual RTAS
+"firmware" blob in the guest is a small stub of a few instructions which
+calls our private H_RTAS hypervisor call to pass the RTAS calls to QEMU.
+
+Arguments:
+
+  r3 : H_RTAS (0xf000)
+  r4 : Guest physical address of RTAS parameter block
+
+Returns:
+
+  H_SUCCESS   : Successully called the RTAS function (RTAS result
+                will have been stored in the parameter block)
+  H_PARAMETER : Unknown token
+
+- H_LOGICAL_MEMOP (0xf001)
+
+When the guest runs in "real mode" (in powerpc lingua this means
+with MMU disabled, ie guest effective == guest physical), it only
+has access to a subset of memory and no IOs.
+
+PAPR provides a set of hypervisor calls to perform cachable or
+non-cachable accesses to any guest physical addresses that the
+guest can use in order to access IO devices while in real mode.
+
+This is typically used by the firmware running in the guest.
+
+However, doing a hypercall for each access is extremely inefficient
+(even more so when running KVM) when accessing the frame buffer. In
+that case, things like scrolling become unusably slow.
+
+This hypercall allows the guest to request a "memory op" to be applied
+to memory. The supported memory ops at this point are to copy a range
+of memory (supports overlap of source and destination) and XOR which
+is used by our SLOF firmware to invert the screen.
+
+Arguments:
+
+  r3: H_LOGICAL_MEMOP (0xf001)
+  r4: Guest physical address of destination
+  r5: Guest physical address of source
+  r6: Individual element size
+        0 = 1 byte
+        1 = 2 bytes
+        2 = 4 bytes
+        3 = 8 bytes
+  r7: Number of elements
+  r8: Operation
+        0 = copy
+        1 = xor
+
+Returns:
+
+  H_SUCCESS   : Success
+  H_PARAMETER : Invalid argument
+

hw/spapr.c

@@ -197,6 +197,7 @@ static void *spapr_create_fdt_skel(const char *cpu_model,
     uint32_t pft_size_prop[] = {0, cpu_to_be32(hash_shift)};
     char hypertas_prop[] = "hcall-pft\0hcall-term\0hcall-dabr\0hcall-interrupt"
         "\0hcall-tce\0hcall-vio\0hcall-splpar\0hcall-bulk";
+    char qemu_hypertas_prop[] = "hcall-memop1";
     uint32_t interrupt_server_ranges_prop[] = {0, cpu_to_be32(smp_cpus)};
     int i;
     char *modelname;
@@ -417,6 +418,8 @@ static void *spapr_create_fdt_skel(const char *cpu_model,
 
     _FDT((fdt_property(fdt, "ibm,hypertas-functions", hypertas_prop,
                        sizeof(hypertas_prop))));
+    _FDT((fdt_property(fdt, "qemu,hypertas-functions", qemu_hypertas_prop,
+                       sizeof(qemu_hypertas_prop))));
 
     _FDT((fdt_property(fdt, "ibm,associativity-reference-points",
         refpoints, sizeof(refpoints))));

hw/spapr.h

@@ -264,7 +264,8 @@ typedef struct sPAPREnvironment {
  */
 #define KVMPPC_HCALL_BASE       0xf000
 #define KVMPPC_H_RTAS           (KVMPPC_HCALL_BASE + 0x0)
-#define KVMPPC_HCALL_MAX        KVMPPC_H_RTAS
+#define KVMPPC_H_LOGICAL_MEMOP  (KVMPPC_HCALL_BASE + 0x1)
+#define KVMPPC_HCALL_MAX        KVMPPC_H_LOGICAL_MEMOP
 
 extern sPAPREnvironment *spapr;
 

hw/spapr_hcall.c

@@ -608,6 +608,73 @@ static target_ulong h_logical_store(CPUPPCState *env, sPAPREnvironment *spapr,
     return H_PARAMETER;
 }
 
+static target_ulong h_logical_memop(CPUPPCState *env, sPAPREnvironment *spapr,
+                                    target_ulong opcode, target_ulong *args)
+{
+    target_ulong dst   = args[0]; /* Destination address */
+    target_ulong src   = args[1]; /* Source address */
+    target_ulong esize = args[2]; /* Element size (0=1,1=2,2=4,3=8) */
+    target_ulong count = args[3]; /* Element count */
+    target_ulong op    = args[4]; /* 0 = copy, 1 = invert */
+    uint64_t tmp;
+    unsigned int mask = (1 << esize) - 1;
+    int step = 1 << esize;
+
+    if (count > 0x80000000) {
+        return H_PARAMETER;
+    }
+
+    if ((dst & mask) || (src & mask) || (op > 1)) {
+        return H_PARAMETER;
+    }
+
+    if (dst >= src && dst < (src + (count << esize))) {
+            dst = dst + ((count - 1) << esize);
+            src = src + ((count - 1) << esize);
+            step = -step;
+    }
+
+    while (count--) {
+        switch (esize) {
+        case 0:
+            tmp = ldub_phys(src);
+            break;
+        case 1:
+            tmp = lduw_phys(src);
+            break;
+        case 2:
+            tmp = ldl_phys(src);
+            break;
+        case 3:
+            tmp = ldq_phys(src);
+            break;
+        default:
+            return H_PARAMETER;
+        }
+        if (op == 1) {
+            tmp = ~tmp;
+        }
+        switch (esize) {
+        case 0:
+            stb_phys(dst, tmp);
+            break;
+        case 1:
+            stw_phys(dst, tmp);
+            break;
+        case 2:
+            stl_phys(dst, tmp);
+            break;
+        case 3:
+            stq_phys(dst, tmp);
+            break;
+        }
+        dst = dst + step;
+        src = src + step;
+    }
+
+    return H_SUCCESS;
+}
+
 static target_ulong h_logical_icbi(CPUPPCState *env, sPAPREnvironment *spapr,
                                    target_ulong opcode, target_ulong *args)
 {
@@ -700,6 +767,7 @@ static void hypercall_register_types(void)
     spapr_register_hypercall(H_LOGICAL_CACHE_STORE, h_logical_store);
     spapr_register_hypercall(H_LOGICAL_ICBI, h_logical_icbi);
     spapr_register_hypercall(H_LOGICAL_DCBF, h_logical_dcbf);
+    spapr_register_hypercall(KVMPPC_H_LOGICAL_MEMOP, h_logical_memop);
 
     /* qemu/KVM-PPC specific hcalls */
     spapr_register_hypercall(KVMPPC_H_RTAS, h_rtas);